CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

muapi-talking-baby-video

Create a viral-style video of a talking baby with custom costumes and scripts.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./library/motion/talking-baby-video/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is an efficient, well-structured two-phase recipe with concrete prompts, models, and a fallback API path, plus a user-approval checkpoint between phases. Its only notable gaps are incomplete command-line syntax for the muapi calls and an unresolved either/or model and aspect-ratio choice, which keep actionability and workflow clarity just below top marks.

DimensionReasoningScore

Conciseness

The body is lean and every section earns its place: an inputs table, two compact phases, trigger keywords, and short agent notes. There is no explanation of concepts Claude already knows and no padding, matching anchor 5 ('Lean and efficient; every token earns its place').

5 / 5

Actionability

Guidance is mostly executable — specific commands ('muapi image generate' model='nano-banana', 'muapi video from-image' model='grok-imagine-image-to-video'), verbatim prompts, aspect ratios, and a curl fallback with polling. It falls short of anchor 5 because complete invocation lines with argument syntax are not shown, and either/or choices (e.g. 'nano-banana' or 'wan2.5-text-to-image', '9:16 or 1:1') are left unresolved without selection guidance.

4 / 5

Workflow Clarity

The two-phase sequence is clearly ordered with an explicit human-approval checkpoint ('Present the baby image to the user for approval') between generation and animation. Below anchor 5 because there is no verification step on the final video output (e.g. checking the result exists/failed before presenting); this is not a destructive or batch operation, so the cap at 3 does not apply.

4 / 5

Progressive Disclosure

The skill is under 50 lines, single-purpose, and organized into clear sections (Inputs, Steps, Trigger Keywords, Notes) with no bundle files needed — per the rubric's simple-skill exception, this scores 5. There are no external references, so no nesting or navigation concerns arise.

5 / 5

Total

18

/

20

Passed

Description

57%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is distinctive and concrete about what the skill does, but it omits any 'when to use' trigger guidance and covers only a single action, which limits specificity and completeness. Folding a 'Use when the user wants a funny/talking baby video...' clause into the description would address the two lowest-scoring dimensions.

Suggestions

Add an explicit trigger clause to the description, e.g. 'Use when the user wants a funny or viral-style talking baby video, animated baby character, or baby in a costume speaking lines.'

Enumerate the concrete actions performed (generate the baby character image, animate it speaking a script with a chosen costume) rather than a single 'create a video' verb.

Surface 1-2 natural synonyms or phrasings users would say (e.g. 'make a baby talk', 'baby voiceover video') to improve trigger term coverage within the description itself.

DimensionReasoningScore

Specificity

The description states one concrete action — 'Create a viral-style video of a talking baby with custom costumes and scripts' — but does not list several specific actions. This matches anchor 3 ('Names domain and 1-2 concrete actions, but not comprehensive'); it is below anchor 4 because no action list is enumerated, and above anchor 2 because the domain and action are concrete rather than generic.

3 / 5

Completeness

The 'what' is clear (create a talking-baby video with costumes and scripts) but there is no 'Use when...' clause or equivalent trigger guidance — per judging guidelines this caps completeness at 3. Not 4 because 'when' is entirely absent rather than merely implicit; not 2 because the 'what' is specific and unambiguous.

3 / 5

Trigger Term Quality

Phrases like 'talking baby', 'video', and 'costumes' are natural terms a user might say, but the description lacks common variations and synonyms. This fits anchor 3 ('Some relevant keywords but missing common variations or synonyms') better than anchor 4, which expects fuller coverage such as the trigger keywords section only present in the body.

3 / 5

Distinctiveness Conflict Risk

'Talking baby video' is a clear niche with distinct triggers (viral-style talking baby, costumes, scripts) and minimal overlap risk with other skills. This clearly matches anchor 5; a lower score would require broader overlap, which a talking-baby video generator does not have.

5 / 5

Total

14

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

SamurAIGPT/Generative-Media-Skills

Path

library/motion/talking-baby-video/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.